- authors: Débora Nasser Diniz, Rafael Ferreira Vitor, Andrea Gomes Campos Bianchi, Saul Emanuel Delabrida Silva, Cláudia Martins Carneiro, Daniela Mayumi Ushizima, Fátima Nelsizeuma Sombra de Medeiros, Marcone Jamilson Freitas Souza
- paper source: [link]
- data: [[link]]
- codes: COMING SOON
SLIC result |
This work proposes an ensemble method for cervical nuclei detection, aimed to reduce the workload of cytopathologists. First, a preprocessing phase divides the original image into superpixels, which are input to feature extraction and selection algorithms. The proposed ensemble method combines three classifiers: Decision Tree (DT), Nearest Centroid (NC), and k-Nearest Neighbors (k-NN)., which are evaluated against the ISBI'14 Overlapping Cervical Cytology Image Segmentation Challenge dataset. On the left, we show a result of Simple Linear Iterative Clustering Algorithm (SLIC) in obtaining superpixels. More updates soon! |